DE eng

Search in the Catalogues and Directories

Page: 1 2
Hits 1 – 20 of 24

1
Universal Dependencies 2.9
Zeman, Daniel; Nivre, Joakim; Abrams, Mitchell. - : Universal Dependencies Consortium, 2021
BASE
Show details
2
Universal Dependencies 2.8.1
Zeman, Daniel; Nivre, Joakim; Abrams, Mitchell. - : Universal Dependencies Consortium, 2021
BASE
Show details
3
Universal Dependencies 2.8
Zeman, Daniel; Nivre, Joakim; Abrams, Mitchell. - : Universal Dependencies Consortium, 2021
BASE
Show details
4
The Impact of Positional Encodings on Multilingual Compression ...
BASE
Show details
5
The Impact of Positional Encodings on Multilingual Compression ...
BASE
Show details
6
Attention Can Reflect Syntactic Structure (If You Let It) ...
BASE
Show details
7
Universal Dependencies 2.7
Zeman, Daniel; Nivre, Joakim; Abrams, Mitchell. - : Universal Dependencies Consortium, 2020
BASE
Show details
8
Universal Dependencies 2.6
Zeman, Daniel; Nivre, Joakim; Abrams, Mitchell. - : Universal Dependencies Consortium, 2020
BASE
Show details
9
The Sensitivity of Language Models and Humans to Winograd Schema Perturbations ...
BASE
Show details
10
From Zero to Hero: On the Limitations of Zero-Shot Cross-Lingual Transfer with Multilingual Transformers ...
Lauscher, Anne; Ravishankar, Vinit; Vulic, Ivan. - : Apollo - University of Cambridge Repository, 2020
BASE
Show details
11
From Zero to Hero: On the Limitations of Zero-Shot Cross-Lingual Transfer with Multilingual Transformers ...
BASE
Show details
12
Do Neural Language Models Show Preferences for Syntactic Formalisms? ...
BASE
Show details
13
From Zero to Hero: On the Limitations of Zero-Shot Cross-Lingual Transfer with Multilingual Transformers
Ravishankar, Vinit; Glavas, Goran; Lauscher, Anne; Vulic, Ivan. - : Association for Computational Linguistics, 2020. : Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP 2020), 2020
Abstract: Massively multilingual transformers (MMTs) pretrained via language modeling (e.g., mBERT, XLM-R) have become a default paradigm for zero-shot language transfer in NLP, offering unmatched transfer performance. Current evaluations, however, verify their efficacy in transfers (a) to languages with sufficiently large pretraining corpora, and (b) between close languages. In this work, we analyze the limitations of downstream language transfer with MMTs, showing that, much like cross-lingual word embeddings, they are substantially less effective in resource-lean scenarios and for distant languages. Our experiments, encompassing three lower-level tasks (POS tagging, dependency parsing, NER) and two high-level tasks (NLI, QA), empirically correlate transfer performance with linguistic proximity between source and target languages, but also with the size of target language corpora used in MMT pretraining. Most importantly, we demonstrate that the inexpensive few-shot transfer (i.e., additional fine-tuning on a few target-language instances) is surprisingly effective across the board, warranting more research efforts reaching beyond the limiting zero-shot conditions.
URL: https://doi.org/10.17863/CAM.62210
https://www.repository.cam.ac.uk/handle/1810/315103
BASE
Hide details
14
From zero to hero: On the limitations of zero-shot language transfer with multilingual transformers
Ravishankar, Vinit; Glavaš, Goran; Lauscher, Anne. - : Association for Computational Linguistics, 2020
BASE
Show details
15
Universal Dependencies 2.5
Zeman, Daniel; Nivre, Joakim; Abrams, Mitchell. - : Universal Dependencies Consortium, 2019
BASE
Show details
16
Universal Dependencies 2.4
Nivre, Joakim; Abrams, Mitchell; Agić, Željko. - : Universal Dependencies Consortium, 2019
BASE
Show details
17
Probing Multilingual Sentence Representations With X-Probe ...
BASE
Show details
18
The WMT'18 Morpheval test suites for English-Czech, English-German, English-Finnish and Turkish-English
In: Proceedings of the Third Conference on Machine Translation ; 3rd Conference on Machine Translation (WMT 18) ; https://hal.archives-ouvertes.fr/hal-01910244 ; 3rd Conference on Machine Translation (WMT 18), Oct 2018, Bruxelles, Belgium. pp.550-564, ⟨10.18653/v1/W18-64060⟩ ; http://www.statmt.org/wmt18/ (2018)
BASE
Show details
19
Universal Dependencies 2.2
In: https://hal.archives-ouvertes.fr/hal-01930733 ; 2018 (2018)
BASE
Show details
20
Universal Dependencies 2.3
Nivre, Joakim; Abrams, Mitchell; Agić, Željko. - : Universal Dependencies Consortium, 2018
BASE
Show details

Page: 1 2

Catalogues
0
0
0
0
0
0
0
Bibliographies
0
0
0
0
0
0
0
0
0
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
24
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern